paper-with-me

Papers

Provable Compositional Generalization for Object-Centric Learning

2023-10-09 · Thaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel

Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learning object-centric representations, which are widely conjectured to enable compositional generalization. Yet, it remains unclear when this conjecture will be true, as a principled theoretical or empirical understanding of compositional generalization is lacking. In this work, we investigate when compositional generalization is guaranteed for object-centric representations through the lens of identifiability theory. We show that autoencoders that satisfy structural assumptions on the decoder and enforce encoder-decoder consistency will learn object-centric representations that provably generalize compositionally. We validate our theoretical result and highlight the practical relevance of our assumptions through experiments on synthetic image data.

📄 PDF Abstract BibTeX arXiv:2310.05327

Code (1)

brendel-group/objects-compositional-generalization 공식 구현 pytorch

Tasks

DecoderObject

Similar Papers 제목 키워드 기반

Are Object-Centric Representations Better At Compositional Generalization?

2026-02-18 · Ferdinand Kapl, Amir Mohammad Karimi Mamaghan, Maximilian Seitzer, Karl Henrik Johansson 외 arxiv

Compositional generalization, the ability to reason about novel combinations of familiar concepts, is fundamental to human cognition and a critical challenge for machine learning. Object-centric (OC) representations, whi…

Visual Question Answering

Learning to Compose: Improving Object Centric Learning by Injecting Compositionality

2024-05-01 · Whie Jung, Jaehoon Yoo, Sungjin Ahn, Seunghoon Hong

Learning compositional representation is a key aspect of object-centric learning as it enables flexible systematic generalization and supports complex visual reasoning. However, most of the existing approaches rely on au…

ObjectSystematic GeneralizationvalidVisual Reasoning

On Provable Length and Compositional Generalization

2024-02-07 · Kartik Ahuja, Amin Mansouri

Out-of-distribution generalization capabilities of sequence-to-sequence models can be studied from the lens of two crucial forms of generalization: length generalization -- the ability to generalize to longer sequences t…

DiversityOut-of-Distribution GeneralizationState Space Models

Provably Learning Object-Centric Representations

2023-05-23 · Jack Brady, Roland S. Zimmermann, Yash Sharma, Bernhard Schölkopf 외

Learning structured representations of the visual world in terms of objects promises to significantly improve the generalization abilities of current machine learning models. While recent efforts to this end have shown p…

ObjectRepresentation Learning

EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation

2024-12-25 · Carl Qi, Dan Haramati, Tal Daniel, Aviv Tamar 외

Object manipulation is a common component of everyday tasks, but learning to manipulate objects from high-dimensional observations presents significant challenges. These challenges are heightened in multi-object environm…

ObjectZero-shot Generalization